Category

Retrieval: RL environments and AI benchmarks

AI benchmarks
35
Shares entries with
1 category

Snapshot 2026-10-11. How categories are built · Where the data comes from

In short

What are RL environments for retrieval?
A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models.

Only benchmarks use the Retrieval tag: the RL environment directories file their vendors under other categories. Browse all RL environments.

AI benchmarks 35

None confirmed yet.

35 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
  1. HAKARI-Bench
  2. IdioLink
  3. MRBench
  4. SkillRet
  5. RTEB
  6. Sefaria Rabbinic Embedding Leaderboard
  7. FollowTable
  8. SABER-Math
  9. CoREB
  10. ArguAna
  11. IMLogic
  12. MMed-Bench-IR
  13. PrecisionMemBench
  14. Reproducing Complex Set-Compositional Information Retrieval
  15. Rethinking Reasoning-Intensive Retrieval
  16. Agentset Reranker Leaderboard
  17. ChatRAG Bench
  18. RadLIT-9
  19. STaRK
  20. ViDoRe V3 Pipeline
  21. AGGBench
  22. EDIR
  23. FORCEBENCH
  24. OBLIQ-Bench
  25. PosIR
  26. Re$^2$Math
  27. WildGraphBench
  28. BRIGHT
  29. MemoryQuest
  30. FEVEROUS
  31. RAGBench
  32. Beyond Known Facts
  33. CiteCheck
  34. CORTEX
  35. FAB-Bench

Domains that overlap with Retrieval

Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.